dasf.ml.inference.loader.torch
==============================

.. py:module:: dasf.ml.inference.loader.torch


Classes
-------

.. autoapisummary::

   dasf.ml.inference.loader.torch.TorchLoader


Module Contents
---------------

.. py:class:: TorchLoader(model_class_or_file, dtype=torch.float32, checkpoint=None, device=None)

   Bases: :py:obj:`dasf.ml.inference.loader.base.BaseLoader`


   Model Loader for Torch models

   model_class_or_file: class or file with model definition
   dtype: data type of model input
   checkpoint: model chekpoint file
   device: device to place model ("cpu" or "gpu")


   .. py:attribute:: model_class_or_file


   .. py:attribute:: dtype


   .. py:attribute:: checkpoint


   .. py:attribute:: device


   .. py:method:: load_model(**kwargs)

      Load Model method is specific for each framework/model.



   .. py:method:: inference(model, data)